easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update go-jsonnet for linter bugfix

Browse Source
This commit is contained in:
Haoyu Sun
2021-10-09 21:07:37 +02:00
parent 10c11d5019
commit 1e632d2ec8
17 changed files with 10070 additions and 3236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
manifests/prometheus-prometheusRule.yaml
View File

@@ -16,7 +16,8 @@ spec:
rules:
- alert: PrometheusBadConfig
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to
reload its configuration.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusbadconfig
summary: Failed Prometheus configuration reload.
expr: |
@@ -28,9 +29,11 @@ spec:
severity: critical
- alert: PrometheusNotificationQueueRunningFull
annotations:
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full.
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}}
is running full.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotificationqueuerunningfull
summary: Prometheus alert notification queue predicted to run full in less than 30m.
summary: Prometheus alert notification queue predicted to run full in less
than 30m.
expr: |
# Without min_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
@@ -44,9 +47,11 @@ spec:
severity: warning
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
annotations:
description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.'
description: '{{ printf "%.1f" $value }}% errors while sending alerts from
Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstosomealertmanagers
summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager.
summary: Prometheus has encountered more than 1% errors sending alerts to
a specific Alertmanager.
expr: |
(
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
@@ -60,7 +65,8 @@ spec:
severity: warning
- alert: PrometheusNotConnectedToAlertmanagers
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected
to any Alertmanagers.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotconnectedtoalertmanagers
summary: Prometheus is not connected to any Alertmanagers.
expr: |
@@ -72,7 +78,8 @@ spec:
severity: warning
- alert: PrometheusTSDBReloadsFailing
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
{{$value | humanize}} reload failures over the last 3h.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing
summary: Prometheus has issues reloading blocks from disk.
expr: |
@@ -82,7 +89,8 @@ spec:
severity: warning
- alert: PrometheusTSDBCompactionsFailing
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
{{$value | humanize}} compaction failures over the last 3h.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbcompactionsfailing
summary: Prometheus has issues compacting blocks.
expr: |
@@ -92,7 +100,8 @@ spec:
severity: warning
- alert: PrometheusNotIngestingSamples
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting
samples.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotingestingsamples
summary: Prometheus is not ingesting samples.
expr: |
@@ -110,7 +119,9 @@ spec:
severity: warning
- alert: PrometheusDuplicateTimestamps
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
{{ printf "%.4g" $value }} samples/s with different values but duplicated
timestamp.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps
summary: Prometheus is dropping samples with duplicate timestamps.
expr: |
@@ -120,7 +131,8 @@ spec:
severity: warning
- alert: PrometheusOutOfOrderTimestamps
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
{{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps
summary: Prometheus drops samples with out-of-order timestamps.
expr: |
@@ -130,7 +142,9 @@ spec:
severity: warning
- alert: PrometheusRemoteStorageFailures
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send
{{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{
$labels.url }}
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures
summary: Prometheus fails to send samples to remote storage.
expr: |
@@ -150,7 +164,9 @@ spec:
severity: critical
- alert: PrometheusRemoteWriteBehind
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url
}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind
summary: Prometheus remote write is behind.
expr: |
@@ -167,9 +183,14 @@ spec:
severity: critical
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` $labels.instance | query | first | value }}.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
desired shards calculation wants to run {{ $value }} shards for queue {{
$labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{
printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
$labels.instance | query | first | value }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
summary: Prometheus remote write desired shards calculation wants to run more
than configured max shards.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
@@ -183,7 +204,8 @@ spec:
severity: warning
- alert: PrometheusRuleFailures
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to
evaluate {{ printf "%.0f" $value }} rules in the last 5m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures
summary: Prometheus is failing rule evaluations.
expr: |
@@ -193,7 +215,8 @@ spec:
severity: critical
- alert: PrometheusMissingRuleEvaluations
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{
printf "%.0f" $value }} rule group evaluations in the last 5m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
expr: |
@@ -203,9 +226,12 @@ spec:
severity: warning
- alert: PrometheusTargetLimitHit
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped
{{ printf "%.0f" $value }} targets because the number of targets exceeded
the configured target_limit.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit
summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit.
summary: Prometheus has dropped targets because some scrape configs have exceeded
the targets limit.
expr: |
increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 15m
@@ -213,9 +239,12 @@ spec:
severity: warning
- alert: PrometheusLabelLimitHit
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped
{{ printf "%.0f" $value }} targets because some samples exceeded the configured
label_limit, label_name_length_limit or label_value_length_limit.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuslabellimithit
summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit.
summary: Prometheus has dropped targets because some scrape configs have exceeded
the labels limit.
expr: |
increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
for: 15m
@@ -223,7 +252,8 @@ spec:
severity: warning
- alert: PrometheusTargetSyncFailure
annotations:
description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}} have failed to sync because invalid configuration was supplied.'
description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}}
have failed to sync because invalid configuration was supplied.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetsyncfailure
summary: Prometheus has failed to sync targets.
expr: |
@@ -233,7 +263,8 @@ spec:
severity: critical
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts
from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstoanyalertmanager
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |